Sighting telescope self-adaptive aiming method and system based on intelligent sensing

Abstract

The invention provides a sighting telescope self-adaptive sighting method and system based on intelligent sensing, and relates to the technical field of optical elements, and the method comprises the steps that sighting influence factors influencing sighting are determined and at least comprise the target distance, the sighting angle, the wind speed and direction and the atmospheric pressure; establishing an influence factor matrix, collecting real-time data through an intelligent sensor combination, and filling to generate a real-time influence factor matrix; a historical aiming data set is collected, and a factor change model of each factor is constructed; analyzing the real-time influence factor matrix, calculating change characteristics of each factor, and generating an analysis result matrix; according to the analysis result matrix, self-adaptive calibration analysis is carried out, and self-adaptive aiming parameters are generated; and carrying out self-adaptive aiming control on the sighting telescope. The technical problem that the existing aiming technology generally depends on manual adjustment or static calibration and lacks real-time adaptability to environmental changes, so that the aiming precision is insufficient is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of optical elements, and particularly to an adaptive aiming method and system for a telescopic sight based on intelligent sensing. Background Art

[0002] As an optical device, a telescopic sight is widely used in various fields that require high-precision target positioning and measurement. For example, in the process of industrial automation, the telescopic sight is used for precise positioning and detection to improve production efficiency and product quality. However, existing telescopic sight systems usually rely on manual adjustment or static calibration and are difficult to adapt to environmental changes in real time. This method cannot fully cope with the dynamic changes of factors such as target distance, angle change, and environmental illumination, resulting in insufficient accuracy of positioning and measurement. Moreover, traditional telescopic sight systems often lack intelligent feedback and dynamic adjustment mechanisms and cannot perform adaptive adjustment based on real-time data, so they cannot maintain high-precision positioning and measurement in complex environments. Minor changes in the environment or the target may lead to large errors. Summary of the Invention

[0003] This application provides an adaptive aiming method and system for a telescopic sight based on intelligent sensing, aiming to solve the technical problem that existing aiming technologies usually rely on manual adjustment or static calibration and lack real-time adaptability to environmental changes, resulting in insufficient aiming accuracy.

[0004] In the first aspect disclosed in this application, an adaptive aiming method for a telescopic sight based on intelligent sensing is provided. The method includes: determining aiming influencing factors that affect aiming, where the aiming influencing factors at least include target distance, aiming angle, wind speed and direction, and atmospheric pressure; establishing an influencing factor matrix according to the aiming influencing factors, and collecting real-time data through an intelligent sensor combination to fill the influencing factor matrix and generate a real-time influencing factor matrix; collecting a historical aiming data set, and constructing a factor change model for each factor based on the historical aiming data set, where the factor change model is used to describe the change trend and influence degree of each factor; based on the factor change model, analyzing the real-time influencing factor matrix, calculating the change characteristics of each factor, and generating an analysis result matrix, where each factor in the analysis result matrix corresponds to a change characteristic value; according to the analysis result matrix, performing adaptive calibration analysis to generate adaptive aiming parameters, where the adaptive aiming parameters include an optimized control value for each factor; and performing adaptive aiming control of the telescopic sight according to the adaptive aiming parameters.

[0005] The second aspect disclosed in this application provides an adaptive aiming system for a telescopic sight based on intelligent sensing. The system is used for the above-mentioned adaptive aiming method for a telescopic sight based on intelligent sensing, and the system includes: an influencing factor determination module, which is used to determine the aiming influencing factors that affect aiming. Among them, the aiming influencing factors at least include target distance, aiming angle, wind speed and direction, and atmospheric pressure; a factor matrix construction module, which is used to establish an influencing factor matrix according to the aiming influencing factors, and collect real-time data through an intelligent sensor combination to fill the influencing factor matrix and generate a real-time influencing factor matrix; a change model construction module, which is used to collect a set of historical aiming data and construct a factor change model for each factor based on the set of historical aiming data. Among them, the factor change model is used to describe the change trend and influence degree of each factor; a change characteristic calculation module, which is used to analyze the real-time influencing factor matrix based on the factor change model, calculate the change characteristics of each factor, and generate an analysis result matrix. Among them, each factor in the analysis result matrix corresponds to a change characteristic value; a calibration analysis module, which is used to perform adaptive calibration analysis according to the analysis result matrix and generate adaptive aiming parameters. Among them, the adaptive aiming parameters include the optimized control value of each factor; an aiming control module, which is used to perform adaptive aiming control of the telescopic sight according to the adaptive aiming parameters.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: Real-time data such as target distance, aiming angle, wind speed and direction, and atmospheric pressure are collected through intelligent sensors, and these data are filled into the influencing factor matrix to generate a real-time influencing factor matrix, ensuring the timeliness and accuracy of the data; based on the set of historical aiming data, change models for each factor are constructed, and these models are used to describe the change trend and influence degree of each factor, ensuring the accuracy of aiming; the real-time influencing factor matrix is analyzed, the change characteristics of each factor are calculated, and an analysis result matrix is generated. Through these analysis results, the influence of environmental changes on aiming can be understood in real time; according to the analysis result matrix, adaptive calibration analysis is performed to generate adaptive aiming parameters, and these parameters include the optimized control value of each factor, which can effectively cope with the changes of environmental factors; according to the adaptive aiming parameters, the telescopic sight is adjusted to ensure the accuracy and stability of aiming. Through the dynamic adjustment of the optimized control value, a rapid response to environmental changes is achieved; the gradient descent method and adaptive step size adjustment are used to iteratively optimize the initial aiming parameters to ensure the minimization of aiming errors and improve the performance and reliability of the aiming system. Finally, high-precision and adaptive aiming control are achieved, significantly improving the performance and reliability of the aiming system.

[0007] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specifically gives the specific implementation manners of this application. Description of the Drawings

[0008] Figure 1 It is a schematic flowchart of the adaptive aiming method for a telescopic sight based on intelligent sensing provided by an embodiment of this application; Figure 2 It is a schematic structural diagram of the adaptive aiming system for a telescopic sight based on intelligent sensing provided by an embodiment of this application.

[0009] Description of the reference numerals: the influencing factor determination module 10, the factor matrix construction module 20, the change model construction module 30, the change characteristic calculation module 40, the calibration analysis module 50, and the aiming control module 60. Detailed Description of the Preferred Embodiments

[0010] By providing an adaptive aiming method for a telescopic sight based on intelligent sensing in an embodiment of this application, the technical problem that the existing aiming technology usually relies on manual adjustment or static calibration, lacks real-time adaptability to environmental changes, and results in insufficient aiming accuracy is solved.

[0011] After introducing the basic principle of this application, the following will specifically introduce various non-limiting implementation manners of this application in combination with the drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application.

[0012] As Figure 1 shown, an embodiment of this application provides an adaptive aiming method for a telescopic sight based on intelligent sensing, and the method includes: Determine the aiming influencing factors that affect aiming, where the aiming influencing factors at least include the target distance, the aiming angle, the wind speed and direction, and the atmospheric pressure.

[0013] Based on the theoretical knowledge of physics and ballistics, analyze which factors will affect the ballistic trajectory during aiming, including the target distance, the aiming angle, the wind speed and direction, and the atmospheric pressure, etc. For example, the farther the target distance, the greater the influence of various environmental factors; the wind speed and direction will have a significant impact on the lateral deviation. Generate the aiming influencing factors according to the analysis results to provide a reliable basis for adaptive aiming.

[0014] Establish an influence factor matrix according to the aiming influencing factors, and collect real-time data through a combination of intelligent sensors to fill the influence factor matrix and generate a real-time influence factor matrix.

[0015] The influence factor matrix is used to record and represent all the influence factors related to aiming. The values of each influence factor at different time points form the elements of the matrix. The rows of the matrix represent different influence factors, and the columns represent the data at different time points.

[0016] Select appropriate sensors according to each influence factor. For example, select a laser rangefinder or a radar sensor to collect the target distance; select a gyroscope or an electronic compass to collect the aiming angle; select an anemometer and a wind vane to collect the wind speed and direction; select a barometric pressure sensor to collect the atmospheric pressure. Install the sensors in appropriate positions to ensure that the data of each influence factor can be accurately measured. For example, the wind speed and direction sensors should be installed in an open area to avoid interference from obstacles. Calibrate all the sensors, collect the sensor data regularly through a data acquisition system, and fill the collected data into the corresponding positions of the influence factor matrix in chronological order to generate a real-time influence factor matrix.

[0017] Collect a set of historical aiming data, and build a factor change model for each factor based on the set of historical aiming data. Among them, the factor change model is used to describe the change trend and influence degree of each factor.

[0018] Collect a set of historical aiming data, including aiming data collected through experiments under different environmental conditions, aiming data collected from actual use, and data collected from training. The collected data includes environmental data and aiming results. The aiming results also include the actual aiming point, the hitting point, the hitting deviation, etc.

[0019] Use clustering algorithms such as K-means and DBSCAN to cluster the historical data according to environmental conditions, and identify the aiming data patterns under different environmental conditions. For each clustering interval, calculate the probability distribution function of each factor, and use regression analysis such as linear regression and polynomial regression to establish a relationship model between each factor and the aiming deviation, quantitatively describe the influence of each factor on the aiming result, establish a model of each factor changing over time, and obtain the factor change model for subsequent real-time data analysis and aiming calibration.

[0020] Based on the factor change model, analyze the real-time influence factor matrix, calculate the change characteristics of each factor, and generate an analysis result matrix. Among them, each factor in the analysis result matrix corresponds to a change characteristic value.

[0021] Substitute each data point in the real-time influencing factor matrix into the factor change model. For each real-time data point and its corresponding factor, calculate its distribution probability under the factor change model. Based on the historical data model, calculate the expected value and variance of each factor in its corresponding clustering interval. Combine the real-time data, distribution probability, expected value, and variance to calculate the change characteristic value of each factor. The change characteristic value can be expressed as the degree to which the standardized data point deviates from the expected value. Integrate the change characteristic values of all influencing factors into the analysis result matrix. Each element of the analysis result matrix represents the change characteristic value of the j-th factor corresponding to the i-th data point under the current conditions. This analysis result matrix provides the basic data for adaptive calibration analysis.

[0022] According to the analysis result matrix, perform adaptive calibration analysis to generate adaptive aiming parameters, where the adaptive aiming parameters include the optimized control value of each factor; perform adaptive aiming control of the aiming scope according to the adaptive aiming parameters.

[0023] Set minimizing the aiming error as the optimization goal. The aiming error can be defined as the distance between the actual hitting position and the expected hitting position. Construct an error function that describes the relationship between the aiming error and the change characteristic values of each factor. Set the constraint conditions that need to be satisfied during the optimization process, such as the adjustment range of the aiming scope, physical limitations, etc. Randomly set the initial aiming parameter set, and use the gradient descent method to iteratively optimize the error function until the error function converges to obtain the optimized aiming parameters. As the number of iterations increases, the step size gradually decreases to ensure the stability of the optimization process. When the change of the error function is less than the preset threshold or reaches the maximum number of iterations, terminate the iteration. The finally obtained optimized aiming parameters are the adaptive aiming parameters, which include the optimized control value of each factor.

[0024] Transmit the adaptive aiming parameters to the aiming control system. The aiming control system adjusts the control values of each factor according to the adaptive aiming parameters, including adjusting the angle and position of the aiming scope, adjusting the compensation parameters according to the wind speed and direction, adjusting the ballistic compensation according to the atmospheric pressure and target distance, etc. Through adaptive aiming control, ensure accurate aiming under various environmental conditions.

[0025] Furthermore, the method for constructing the factor change model of each factor based on the historical aiming data set includes: Obtain the calibration influence factor data interval of the sight, where the calibration influence factor data interval is obtained according to the aiming attribute of the sight; based on the calibration influence factor data interval, cluster the historical aiming data set to generate multiple increasing clustering intervals, where each increasing clustering interval corresponds to a calibration influence factor data interval; analyze the distribution of the historical aiming data set according to the multiple increasing clustering intervals, obtain the probability that the historical aiming data set corresponding to each factor falls into each clustering interval, and generate the data distribution probability function corresponding to each factor; integrate the data distribution probability functions of each factor in ascending order to establish the factor change model.

[0026] According to the technical specifications and design parameters of the sight, determine its key aiming attributes. For example, the effective distance range, adjustable angle range, wind speed compensation range, etc. of the sight. Analyze a large amount of historical aiming data, and count the range and distribution of each influence factor. For example, count the minimum value, maximum value and distribution of the target distance in the historical data, count the change range of the aiming angle in the historical data, and analyze the historical data distribution of different wind speeds and wind directions. According to the analysis results of the historical data and the technical specifications of the sight, set the calibration data interval of each influence factor.

[0027] To avoid the influence of data with different dimensions on the clustering results, first normalize all historical data. For example, use the min-max normalization method for processing. Select a clustering algorithm, such as K-means, DBSCAN, hierarchical clustering, etc. Among them, the K-means algorithm is suitable for processing data with obvious clustering centers. Determine the optimal number of clusters k, run the selected clustering algorithm, cluster the historical data into k clusters, and count the data in each cluster to generate multiple clustering intervals of the calibration influence factors. Each interval corresponds to a data range of the calibration influence factor. These intervals are used to construct the factor change model to help describe the change trend and influence degree of each influence factor.

[0028] Count the data in each clustering interval, calculate the distribution probability of each factor in these intervals. For each factor, generate the data distribution probability function of this factor according to the probabilities of different clustering intervals. The data distribution probability function can be represented by methods such as histograms and kernel density estimation. For example, use a distribution function to describe this relationship, and this function can be expressed as the data distribution probability in each clustering interval.

[0029] Integrate the distribution probability functions of each factor in ascending order of the clustering intervals into a complete change model. For each factor, establish a model to describe the change trend of this factor according to its data distribution probability function. For example, it can be represented by methods such as piecewise functions, linear interpolation, and polynomial fitting, and is used to describe the change trend and influence degree of each factor.

[0030] Furthermore, the data distribution probability function has the following formula: ; ; where is any clustering interval among multiple increasing clustering intervals. Let the calibration interval of historical data x be which is divided into n clustering intervals, and each interval is where , is the number of historical data points falling into the interval , is the total number of historical data points, is the probability that historical data falls into any clustering interval , is the indicator function which takes the value of 1 when historical data x falls into the interval and 0 otherwise, is the probability distribution of each clustering interval.

[0031] Specifically, the data distribution probability function has the following formula: ; where, let the calibration interval of historical data x be which is divided into n clustering intervals, and each interval is where For each clustering interval , calculate the probability that historical data falls into this interval. The distribution function can be expressed as the probability distribution of each interval. When historical data x falls into the interval , takes the value of 1, then , otherwise .

[0032] Furthermore, based on the factor change model, parse the real-time impact factor matrix, calculate the change characteristics of each factor, and generate an analysis result matrix. The method includes: Input the first factor in the real-time influencing factor matrix into the data distribution probability function, and calculate the first distribution probability that the first factor falls into the first clustering interval; calculate the first expected value and the first variance value of the first factor in the first clustering interval; obtain the first real-time data of the first factor, and calculate the first change characteristic value of the first factor according to the first real-time data, the first distribution probability, the first expected value, and the first variance value; integrate each change characteristic value of each factor to obtain the analysis result matrix.

[0033] Randomly extract a factor from the real-time influencing factor matrix as the first factor, such as wind speed. Extract the real-time data points of the first factor from the real-time influencing factor matrix. According to the previous data clustering results, divide the calibration interval of the first factor into n clustering intervals, and use the constructed distribution function to calculate the distribution probability that the real-time data points of the first factor fall into the first clustering interval, and obtain the first distribution probability that the first factor falls into the first clustering interval through function calculation.

[0034] Extract all historical data point sets of the first factor in the first clustering interval, and use the expected value formula to calculate the first expected value of the first factor in the first clustering interval and use the variance formula to calculate the first variance value of the first factor in the first clustering interval These information are used to describe the central tendency and dispersion degree of the data.

[0035] Extract the first real-time data point of the first factor, and combine the real-time data, distribution probability, expected value and variance value to calculate the first change characteristic value of the first factor. The change characteristic value can be expressed as the degree to which the standardized data point deviates from the expected value. The formula is as follows: ; where is the first change characteristic value, is the real-time data point, is the first expected value, is the first standard deviation, and the standard deviation is the square root of the variance, is the first distribution probability, and the change characteristic value reflects the degree to which the actual data deviates from the expected value.

[0036] For each influencing factor, repeat the above calculation process, and integrate the change characteristic values of all influencing factors into the analysis result matrix. Each element of the analysis result matrix represents the change characteristic value of the i-th data point corresponding to the j-th factor under the current conditions. The analysis result matrix contains the change characteristic values of each data point and each influencing factor, reflecting the change situations of various factors in the real-time environment and their influence on the aiming process.

[0037] Furthermore, based on the parsed result matrix, an adaptive calibration analysis is performed to generate adaptive aiming parameters. The method includes: Taking minimizing the aiming error as the optimization objective, an optimization model is established based on the parsed result matrix, where the optimization model includes an error function; randomly set an initial aiming parameter set, and based on the error function, use the gradient descent method with a preset parameter update step size to iteratively optimize the initial aiming parameter set until the error function converges, and obtain the optimized aiming parameters as the adaptive aiming parameters.

[0038] Set the optimization objective to minimize the aiming error to ensure the accuracy and stability of aiming. The error function represents the difference between the actual hit position and the expected hit position. Use the mean square error as the error function and establish an optimization model based on the parsed result matrix. The goal of the model is to minimize the error function by adjusting the aiming parameters.

[0039] Randomly set an initial aiming parameter set, including the control parameters of various influencing factors, such as aiming angle, wind speed correction amount, etc., initialize the learning rate and other relevant parameters, such as momentum factor, etc., and calculate the gradient of the error function with respect to each aiming parameter. The calculation formula is as follows: ; where is the number of data points, is the number of data points, The expected hit position of the i-th data point, is the actual hit position of the i-th data point.

[0040] Update the aiming parameters using the gradient descent method. The formula is as follows: , continuously iterate the above steps until the error function converges to a predetermined threshold or the change amount of parameter update is lower than a certain threshold, then stop the iteration, and obtain the optimized aiming parameters. The finally optimized aiming parameters include the optimal aiming angle, wind speed correction amount, wind direction correction amount, etc. Furthermore, the preset parameter update step size decreases as the number of iterations increases. The expression of the preset parameter update step size is as follows: ; where, is the step size after the -th iteration, is the initial step size, is the preset attenuation rate, is the number of iterations that have been performed.

[0041] To improve the stability and convergence speed of the gradient descent method, use a step size that decreases as the number of iterations increases. The expression of the preset parameter update step size is as follows: ; where the step size It gradually decreases during the iteration process, ensuring a larger step size at the beginning for a rapid descent and a smaller step size when approaching the optimal solution for stable convergence until the error function converges.

[0042] Furthermore, the method further includes: After adaptive aiming control, obtain the actual aiming position and the desired aiming position; calculate the position deviation index between the actual aiming position and the desired aiming position; when the position deviation index reaches a preset position deviation, generate aiming deviation information, and perform adaptive calibration optimization based on the aiming deviation information.

[0043] Use high-precision measurement devices, such as laser rangefinders, cameras, etc., to measure the actual hit position after each shot, and determine the desired hit position according to the aiming target and the set aiming point.

[0044] The position deviation index is used to quantify the difference between the actual hit position and the desired hit position. Usually, the Euclidean distance or other appropriate measurement methods are used to calculate the deviation, and the position deviation index is obtained through calculation.

[0045] Set a preset position deviation threshold according to the actual situation and specific requirements. Compare the calculated position deviation index with the preset position deviation threshold. If the position deviation index exceeds the preset position deviation threshold, generate aiming deviation information. Based on the aiming deviation information, perform adaptive calibration optimization, such as using the optimization model and the gradient descent method again to adjust the aiming parameters to minimize the position deviation. Continuously iterate and update until the position deviation index is less than the preset position deviation threshold. Through the above process, the accuracy and stability of the aiming calibration can be ensured, and the performance and reliability of the aiming system can be improved.

[0046] In summary, the adaptive aiming method for a telescopic sight based on intelligent sensing provided by the embodiments of the present application has the following technical effects: Real-time data such as target distance, aiming angle, wind speed and direction, and atmospheric pressure are collected through intelligent sensors, and these data are filled into the influence factor matrix to generate a real-time influence factor matrix, ensuring the timeliness and accuracy of the data; based on the historical aiming data set, a change model for each factor is constructed, and these models are used to describe the change trends and influence degrees of each factor, ensuring the aiming accuracy; the real-time influence factor matrix is analyzed to calculate the change characteristics of each factor, generating an analysis result matrix, and through these analysis results, the influence of environmental changes on aiming can be understood in real time; according to the analysis result matrix, an adaptive calibration analysis is carried out to generate adaptive aiming parameters, and these parameters include the optimized control values of each factor, which can effectively cope with the changes of environmental factors; according to the adaptive aiming parameters, the aiming scope is adjusted to ensure the accuracy and stability of aiming, and through the dynamic adjustment of the optimized control values, a rapid response to environmental changes is achieved; the gradient descent method and adaptive step size adjustment are used to iteratively optimize the initial aiming parameters to ensure the minimization of aiming errors and improve the performance and reliability of the aiming system. Finally, high-precision and adaptive aiming control is achieved, significantly improving the performance and reliability of the aiming system.

[0047] Based on the same inventive concept as the adaptive aiming method for an aiming scope based on intelligent sensing in the foregoing embodiment, as Figure 2 shown, an embodiment of the present application provides an adaptive aiming system for an aiming scope based on intelligent sensing, and the system includes: An influence factor determination module 10, where the influence factor determination module 10 is used to determine the aiming influence factors that affect aiming, and among them, the aiming influence factors at least include target distance, aiming angle, wind speed and direction, and atmospheric pressure; a factor matrix construction module 20, where the factor matrix construction module 20 is used to establish an influence factor matrix according to the aiming influence factors, and collect real-time data through an intelligent sensor combination to fill the influence factor matrix and generate a real-time influence factor matrix; a change model construction module 30, where the change model construction module 30 is used to collect a historical aiming data set and construct a factor change model for each factor based on the historical aiming data set, and among them, the factor change model is used to describe the change trends and influence degrees of each factor; a change characteristic calculation module 40, where the change characteristic calculation module 40 is used to analyze the real-time influence factor matrix based on the factor change model, calculate the change characteristics of each factor, and generate an analysis result matrix, and among them, each factor in the analysis result matrix corresponds to a change characteristic value; a calibration analysis module 50, where the calibration analysis module 50 is used to perform an adaptive calibration analysis according to the analysis result matrix to generate adaptive aiming parameters, and among them, the adaptive aiming parameters include the optimized control values of each factor; an aiming control module 60, where the aiming control module 60 is used to perform adaptive aiming control of the aiming scope according to the adaptive aiming parameters.

[0048] Furthermore, the system further includes a factor change model construction module to perform the following operation steps: Obtain the calibration influence factor data interval of the sight, where the calibration influence factor data interval is obtained according to the aiming attribute of the sight; based on the calibration influence factor data interval, cluster the historical aiming data set to generate a plurality of increasing clustering intervals, where each increasing clustering interval corresponds to a calibration influence factor data interval; analyze the distribution of the historical aiming data set according to the plurality of increasing clustering intervals, obtain the probability that the historical aiming data set corresponding to each factor falls into each clustering interval, and generate a data distribution probability function corresponding to each factor; integrate the data distribution probability functions of each factor in ascending order to establish the factor change model.

[0049] Furthermore, for the data distribution probability function, the formula is as follows: ; ; where is any clustering interval in a plurality of increasing clustering intervals. Let the calibration interval of historical data x be , which is divided into n clustering intervals, and each interval is , where , is the number of historical data points falling into the interval , is the total number of historical data points, is the probability that the historical data falls into any clustering interval , is an indicator function, which takes the value of 1 when the historical data x falls into the interval , and 0 otherwise, is the probability distribution of each clustering interval.

[0050] Furthermore, the system further includes an analysis result matrix acquisition module to perform the following operation steps: Input the first factor in the real-time influence factor matrix into the data distribution probability function, calculate and obtain the first distribution probability that the first factor falls into the first clustering interval; calculate the first expected value and the first variance value of the first factor in the first clustering interval; obtain the first real-time data of the first factor, and calculate and obtain the first change characteristic value of the first factor according to the first real-time data, the first distribution probability, the first expected value, and the first variance value; integrate the change characteristic values of each factor to obtain the analysis result matrix.

[0051] Furthermore, the system further includes an adaptive aiming parameter acquisition module to perform the following operation steps: Taking minimizing the aiming error as the optimization objective, an optimization model is established according to the parsed result matrix, wherein the optimization model includes an error function; an initial aiming parameter set is randomly set, and based on the error function, the gradient descent method is used, and a preset parameter update step size is adopted to iteratively optimize the initial aiming parameter set until the error function converges, and the optimized aiming parameters are obtained as the adaptive aiming parameters.

[0052] Furthermore, the preset parameter update step size decreases as the number of iterations increases, and the expression of the preset parameter update step size is as follows: ; wherein, is the step size after iterations, is the initial step size, is the preset attenuation rate, is the number of iterations that have been performed.

[0053] Furthermore, the system further includes an adaptive calibration optimization module to perform the following operation steps: After the adaptive aiming control, the actual aiming position and the desired aiming position are obtained; the position deviation index between the actual aiming position and the desired aiming position is calculated; when the position deviation index reaches the preset position deviation, aiming deviation information is generated, and adaptive calibration optimization is performed based on the aiming deviation information.

[0054] Through the foregoing detailed description of the adaptive aiming method for a telescopic sight based on intelligent sensing in this specification, those skilled in the art can clearly know the adaptive aiming system for a telescopic sight based on intelligent sensing in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and for the related parts, reference may be made to the description in the method part.

[0055] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. The adaptive aiming method of the sight based on intelligent sensing is characterized in that: The method comprises: Determining aiming influencing factors affecting aiming, wherein the aiming influencing factors at least include target distance, aiming angle, wind speed and direction, and atmospheric pressure; Establishing an influence factor matrix according to the targeting influence factors, and collecting real-time data through a combination of intelligent sensors to fill in the influence factor matrix and generate a real-time influence factor matrix; Collecting a historical targeting data set, and constructing a factor change model for each factor based on the historical targeting data set, wherein the factor change model is used to describe the change trend and impact degree of each factor; Based on the factor change model, the real-time influencing factor matrix is ​​analyzed, the change characteristics of each factor are calculated, and an analysis result matrix is ​​generated, wherein each factor in the analysis result matrix corresponds to a change characteristic value; According to the analytical result matrix, an adaptive calibration analysis is performed to generate adaptive aiming parameters, wherein the adaptive aiming parameters include an optimized control value of each factor; Adaptive aiming control of the sight is performed according to the adaptive aiming parameters.

2. The method for adaptive aiming of a sight based on intelligent sensing as claimed in claim 1, characterized in that: The method of constructing a factor change model for each factor based on the historical targeting data set includes: Acquire a calibration influencing factor data interval of the sight, wherein the calibration influencing factor data interval is acquired according to the aiming attribute of the sight; Based on the calibration influencing factor data interval, clustering the historical targeting data set to generate a plurality of incremental clustering intervals, wherein each incremental clustering interval corresponds to a calibration influencing factor data interval; Analyzing the distribution of the historical targeting data set according to the multiple incremental clustering intervals, obtaining the probability that the historical targeting data set corresponding to each factor falls into each clustering interval, and generating a data distribution probability function of the corresponding factor; The data distribution probability function of each factor is integrated in increasing order to establish the factor variation model.

3. The method for adaptive aiming of a sight based on intelligent sensing as claimed in claim 2, characterized in that: The data distribution probability function is as follows: ; ; in, is any clustering interval among multiple increasing clustering intervals. Let the calibration interval of historical data x be , which is divided into n clustering intervals, each interval is ,in , Is in the range The number of historical data points, is the total number of historical data points, The historical data falls into any clustering interval The probability of Is an indicator function. When the historical data x falls within the interval The value is 1 when , otherwise it is 0. is the probability distribution of each cluster interval.

4. The method for adaptive aiming of a sight based on intelligent sensing as claimed in claim 3, characterized in that: The method of analyzing the real-time influencing factor matrix based on the factor change model, calculating the change characteristics of each factor, and generating an analysis result matrix includes: Inputting a first factor in the real-time influencing factor matrix into the data distribution probability function, and calculating a first distribution probability that the first factor falls into a first clustering interval; Calculating a first expected value and a first variance value of the first factor in the first clustering interval; Acquire first real-time data of the first factor, and calculate a first change characteristic value of the first factor according to the first real-time data, the first distribution probability, the first expected value, and the first variance value; Each change characteristic value of each factor is integrated to obtain the analytical result matrix.

5. The method for adaptive aiming of a sight based on intelligent sensing as claimed in claim 1, characterized in that: The method of performing adaptive calibration analysis according to the analytical result matrix to generate adaptive aiming parameters includes: Taking minimizing the aiming error as the optimization goal, an optimization model is established according to the analytical result matrix, wherein the optimization model includes an error function; An initial aiming parameter set is randomly set, and based on the error function, a gradient descent method is used, and a preset parameter update step size is adopted to iteratively optimize the initial aiming parameter set until the error function converges, thereby obtaining optimized aiming parameters as the adaptive aiming parameters.

6. The method for adaptive aiming of a sight based on intelligent sensing as claimed in claim 5, characterized in that: The preset parameter update step size decreases as the number of iterations increases. The expression of the preset parameter update step size is as follows: ； in, Iteration The next step length, is the initial step size, is the preset decay rate, is the number of iterations.

7. The method for adaptive aiming of a sight based on intelligent sensing as claimed in claim 1, characterized in that: The method further comprises: After adaptive aiming control, the actual aiming position and the expected aiming position are obtained; Calculating a position deviation index between the actual aiming position and the expected aiming position; When the position deviation index reaches a preset position deviation, aiming deviation information is generated, and adaptive calibration optimization is performed based on the aiming deviation information.

8. The adaptive aiming system of the sight based on intelligent sensing is characterized by: The system for implementing the adaptive aiming method of a sight based on intelligent sensing according to any one of claims 1 to 7 comprises: An influencing factor determination module, the influencing factor determination module is used to determine aiming influencing factors affecting aiming, wherein the aiming influencing factors at least include target distance, aiming angle, wind speed and direction, and atmospheric pressure; A factor matrix building module, wherein the factor matrix building module is used to establish an influencing factor matrix according to the targeting influencing factors, and collect real-time data through a combination of intelligent sensors to fill the influencing factor matrix and generate a real-time influencing factor matrix; A change model building module, the change model building module is used to collect a historical targeting data set, and build a factor change model of each factor based on the historical targeting data set, wherein the factor change model is used to describe the change trend and impact degree of each factor; A change characteristic calculation module, the change characteristic calculation module is used to analyze the real-time influencing factor matrix based on the factor change model, calculate the change characteristic of each factor, and generate an analysis result matrix, wherein each factor in the analysis result matrix corresponds to a change characteristic value; A calibration analysis module, the calibration analysis module is used to perform adaptive calibration analysis according to the analytical result matrix to generate adaptive aiming parameters, wherein the adaptive aiming parameters include an optimized control value of each factor; A sighting control module is used to perform adaptive sighting control of the sight according to the adaptive sighting parameters.

Images